Qwen2.5-VL-72B-Instruct
AlibabaOpenQwen
Qwen2.5-VL-72B-Instruct is a vision-language model from Alibaba. It ranks 130 of 167 on LMArena’s overall vision board with 1107±11 from 3,768 votes. License: Qwen.
Key figures
- Developer
- Alibaba
- License
- Qwen
- First seen (our snapshots)
- 2026-10-26
No data: OCR, Diagrams, Homework, Captioning, Entity recognition, Creative writing, Humor.
Who it suits
- Overall #130 of 167: lower half; consider it mainly for cost or deployment reasons.
- Open weights (Qwen): you can self-host it.
Neighbours on the overall board
| # | Model | Score | Votes | License | Δ vs this model |
|---|---|---|---|---|---|
| 127 | SStep-1o Vision 32K (High Res) StepFun | 1122 | 2,833 | Proprietary | +15 |
| 128 |  Claude 3.5 Sonnet (20240620) Anthropic | 1120 | 21,624 | Proprietary | +13 |
| 129 |  Llama 4 Scout 17B 16E Instruct Meta | 1118 | 6,446 | Llama | +11 |
| 130 | Qwen2.5-VL-72B-Instruct Alibaba | 1107 | 3,768 | Qwen | |
| 131 |  Gemini 2.0 Flash-Lite Preview (02-05) Google | 1100 | 3,991 | Proprietary | -7 |
| 132 | Claude 3.5 Haiku (20241022) Anthropic | 1093 | 1,398 | Proprietary | -14 |
| 133 |  GPT-4 Turbo (2024-04-09) OpenAI | 1090 | 13,391 | Proprietary | -17 |
Alternatives · More from Alibaba
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 10 | Qwen3.8-Max Alibaba | 1313 | 9,957 | Proprietary |
| 37 | Qwen3.7-Plus Alibaba | 1278 | 14,212 | Proprietary |
| 44 | Qwen3.8-27B Alibaba | 1269 | 7,614 | Apache 2.0 |
| 54 | Qwen3.5-397B-A17B Alibaba | 1262 | 32,657 | Apache 2.0 |
| 67 | Qwen3-VL-235B-A22B-Instruct Alibaba | 1247 | 12,724 | Apache 2.0 |
Alternatives · Top open-weight models
| # | Model | Score | Votes | License |
|---|---|---|---|---|
| 24 |  GLM-5.3-Flash Z.ai | 1294 | 16,254 | MIT |
| 34 |  Kimi K2.6 Moonshot AI | 1282 | 16,368 | Modified MIT |
| 38 |  DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek | 1278 | 4,100 | MIT |
| 39 | Gemma 4 31B Google | 1276 | 40,219 | Apache 2.0 |
| 44 | Qwen3.8-27B Alibaba | 1269 | 7,614 | Apache 2.0 |
How to read these scores
- If two scores differ by less than their ± intervals, the models are statistically close.
- Each category board is computed independently; do not compare scores across categories.
- Models with few votes move more; ranks of new entries may change.
FAQ
Where does Qwen2.5-VL-72B-Instruct rank among vision models?
Overall rank 130 (1107); English rank 131 (1115); Chinese rank 105 (1107) (LMArena, data as of Oct 26, 2026).
How good is Qwen2.5-VL-72B-Instruct at OCR?
Qwen2.5-VL-72B-Instruct is not on LMArena’s OCR board yet, so there is no score to cite.
Is Qwen2.5-VL-72B-Instruct better with Chinese or English prompts?
Chinese board: #105 of 128 (1107); English board: #131 of 167 (1115). The boards are computed separately, so compare ranks rather than scores.
Is Qwen2.5-VL-72B-Instruct open-weight?
LMArena lists its license as Qwen, not proprietary; check the license text for commercial use.
How far is Qwen2.5-VL-72B-Instruct from #1?
#1 overall is Claude Fable 5 (High) (1325); Qwen2.5-VL-72B-Instruct has 1107, 218 points behind.
Sources
LMArena data published Oct 19, 2026.
Synced here Oct 26, 2026.
Price, context length and release date have no reliable public data here and are not shown; all figures come from snapshots, blanks are –.